Cedric Clyburn

Had one of my most fun sessions yet with @allthingsopen.bsky.social on Local LLM’s, showing how developers can setup their own private RAG, Vibe Coding, and Agentic AI apps (thanks to #MCP) without needing 3rd party models! Ft @podmanio.bsky.social + #vLLM

💻 Slides: red.ht/local-llm

Can’t wait 🙌

⚙️ Deep Dive Monday at #Jfokus — Building with Open Source AI: A Crash Course with @cedricclyburn.com & Legare Kerrisson from Red Hat.

Learn how open models, Linux & Kubernetes empower you to forge your own AI path. 🔥

www.jfokus.se

#DeveloperConference #AI #OpenSource #RedHat #Kubernetes #LLMs

Thanks to @cedricclyburn.com & Christopher Nuland, I'm pretty much impressed with llm-d.ai: a Kubernetes-native distributed inference stack that brings cache-aware routing and disaggregated serving to LLMs.

Watch the full episode to know more: youtu.be/2Wtug1kTwUk

It was a pleasure to join you mate!

Back to my hometown in Raleigh, NC for @allthingsopen.bsky.social this week 🤩 it’ll be a busy time with my Local LLMs talk tomorrow (Developer Room 1, 3:15pm) but we’ve already started with a #WeLoveOpenSource chat and I’ll be at the #RedHat booth tomorrow doing fun live demos 💻

We had a BLAST this weekend in Boston for #DevConfUS and the #vLLM meetup talking all things open source and AI 🚀 from LLM compression, distributed model serving on Kubernetes, RAG/Agentic apps and so much more, the community is what drives things forward, and I’m so grateful!

How to run OpenAI's gpt-oss models locally with RamaLama | Red Hat Developer Learn to run and serve OpenAI's gpt-oss models locally with RamaLama, a CLI tool that automates secure, containerized deployment and GPU optimization

OpenAI’s gpt-oss language model is a beast, and matches models like o3 and o4-mini on coding, tool use, and more 🤯 but how can you run it yourself with zero trust security, in containers + automatic GPU acceleration? The #Ramalama project has you covered: developers.redhat.com/articles/202...

Thank you! 🙌

Containers and #Kubernetes Made Easy Deep Dive into Podman Desktop with Cedric Clyburn In a compelling presentation at Devnexus, Cedric Clyburn guided the audience from the fundamentals of containerization to advanced AI integration using Podma...

Containers & Kubernetes don’t have to be complicated! Check out our recap of @cedricclyburn.bsky.social’s #Devnexus session “Containers and Kubernetes Made Easy: Deep Dive into Podman Desktop”

👉 devnexus.com/posts/contai...

🎟Get Super Early Bird tickets until Sept 1→ devnexus.com

Getting started with llm-d for distributed AI inference | Red Hat Developer llm-d optimizes LLM inference at scale with disaggregated prefill/decode, smart caching, and Kubernetes-native architecture for production environments

Oh! And also this technical “getting started” guide:

Getting started with llm-d: developers.redhat.com/articles/202...

What is llm-d and why do we need it? We're seeing a significant trend: more organizations are bringing their large language model (LLM) infrastructure in-house.

It’s widely known that LLM’s can be costly and difficult to scale, but in the past few weeks I’ve learned about #llm-d, an open source framework for distributed AI inference on Kubernetes & put together this simple explainer blog ⤵️

What is llm-d & Why Do We Need It: www.redhat.com/en/blog/what...

💻 How we scale OSS AI from laptop → prod → drive.google.com/file/d/1HwaI...

Blackjack Blackjack AI-Enhanced Game

🃏 Test open-source AI in a game of Blackjack → blackjack-frontend-blackjack-ai-demo.apps.prod.rhoai.rh-aiservices-bu.com

On desktop, hit the top-right 🔬button to switch between a 1B parameter model on CPU and a 3B parameter model on GPU :)

We keep hearing about open-source AI like GPT-OSS, DeepSeek, Qwen, Llama 🦙 & more: but how do you actually test and scale them?

At #Ai4 in Vegas 🎰, we built a Blackjack coaching game to benchmark small language models on both CPU and GPU via #llama.cpp and #vLLM! I’ll link the slides and demo ⬇️

Can’t wait to be back in my hometown for ATO! 🤩

Cedric Clyburn (@cedricclyburn.bsky.social), Senior Developer Advocate for Red Hat, joins us on stage to share their insights. Don't miss "Everything You Need to Know About Running LLMs Locally" at #AllThingsOpen! 2025.allthingsopen.org/sessions/eve...

WWC25 - One AI API to Power Them All YouTube video by WeAreDevelopers

🎥 One AI API to Power Them All: www.youtube.com/live/hKm5igE...

WWC25 - Self-Hosted LLMs: From Zero to Inference YouTube video by WeAreDevelopers

🎥 Self-Hosted LLMs: From Zero to Inference: www.youtube.com/live/rVWwE9n...

YouTube video by WeAreDevelopers WWC25 - Bootable AI Containers with Podman Desktop

🎥 Bootable AI Containers with Podman Desktop (ft.
@kevindubois.com): www.youtube.com/watch?v=-kDa...

Couldn’t be happier after a busy few days in Berlin for @wearedevelopers.bsky.social World Congress, catching up with friends & hanging out at the #RedHat stage! I’ll link my own developer & AI engineer focused sessions below, featuring @podmanio.bsky.social #vLLM & Meta’s #LlamaStack!

Happy Monday folks! I’m inbound ✈️ to @devbcn.bsky.social where I’ll be speaking about my favorite open source projects @podmanio.bsky.social & @podman-desktop.io to show how simple it can be for developers to move from containers, to pods, to Kubernetes! Join me on July 9th @ 2:20 in Room 2 :)

Back to my roots! I’m here in the NY IBM Technology studio to record a new whiteboard on @podmanio.bsky.social + @podman-desktop.io and #BootableContainers! It’s always a fun time producing these but Bootc is a uniquely special subject :)

Why rent AI when you can run it? Learn how to deploy open-source LLMs locally, optimize performance & integrate with your data with @cedricclyburn.bsky.social at dev2next. Live demos included! 🚀

www.dev2next.com/speaker/e915...

🎟️ dev2next.com
💥 Code JOIN-CEDRICC-50OFF = discount

Enjoy the videos and music that you love, upload original content and share it all with friends, family and the world on YouTube.

📹 Revive la charla «Everything You Need to Know About Running LLMs Locally» por @cedricclyburn.bsky.social, Roberto Carratalá

Thank you! It was an honor to join :)

Discover how to make LLM fine-tuning accessible with InstructLab with this Devoxx UK talk by @cedricclyburn.bsky.social and Legare Kerrison. Learn to refine models for specific use cases on consumer hardware without needing data science expertise.

Watch here - www.devoxx.co.uk//talk?id=8092

YouTube video by Jfokus Everything You Need to Know About Running LLMs Locally by Cedric Clyburn

🎥 Everything You Need to Know About Running LLMs Locally: youtu.be/n1Tc-Z3Drv0

There’s a ✨ revolution ✨ happening in the open source ecosystem around private and local AI systems, which keep your data secure and your costs low (or free)! Earlier this month I joined #AIFokus and the @jfokus.se community to share how developers can get started, recording 🎥⤵️

Woooo! Let’s go 🚀